Planning with the Views via Scene Self-Exploration 事件

Planning with the Views via Scene Self-Exploration arXiv:2605.29563v1 Announce Type: cross Abstract: Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transforms the view, and (2)composing many such transformations across multi-turn plans to identify a target view. We probe both abilities in our proposed ViewSuite, a 3D point-cloud environment on real ScanNet scenes. Acros